At a glance
Moonshot AI's MIT-licensed coding harness provides a terminal UI, structured print mode, multi-provider routing, MCP, skills, plugins, hooks, ACP editor integration, a local web service, installable Computer Use and WebBridge tooling, trace inspection, and parallel foreground or background subagents.
Good choice if
- Parallel coding work that uses foreground, background, or swarm-style subagents
- Teams switching among Kimi, Anthropic, OpenAI-compatible, Gemini, Vertex, and local providers
- One harness shared across a TUI, structured automation, ACP editors, and a local web interface
Check before choosing
- Local shell and file tools run with host privileges; no first-party OS sandbox is documented
- Print mode switches to an unattended auto-permission posture; its background Bash and subagent defaults have no practical wall-clock limit unless configured
- Hooks fail open on errors or timeouts and must not be the sole barrier for high-risk actions
See 5 more considerations
- AgentSwarm can ramp without a configured concurrency cap, while delegated agents inherit the caller's allowed permission rules
- The local web service uses loopback and bearer authentication by default, but --dangerous-bypass-auth exposes sessions, files, and shell access to anyone who can reach the port
- Plugins may inject system-prompt instructions, custom agents, skills, hooks, and MCP servers; third-party and custom sources require explicit trust and user-global installs are not project-scoped
- Kimi Code 0.34.0 preserves completed, cancelled, or failed turn state across server restarts and adds one-click web resume, but session recovery still does not restore repository files or reverse external effects
- Since 0.35.0, the built-in coder subagent no longer delegates recursively by default; custom profiles can still opt in to Agent or AgentSwarm tools and their inherited authority